Maximum Entropy Semi-Supervised Inverse Reinforcement Learning
Abstract
A popular approach to apprenticeship learning (AL) is to formulate it as an inverse reinforcement learning (IRL) problem. The MaxEnt-IRL algorithm successfully integrates the maximum entropy principle into IRL and unlike its predecessors, it resolves the ambiguity arising from the fact that a possibly large number of policies could match the expert's behavior. In this paper, we study an AL setting in which in addition to the expert's trajectories, a number of unsupervised trajectories is available. We introduce MESSI, a novel algorithm that combines MaxEnt-IRL with principles coming from semi-supervised learning. In particular, MESSI integrates the unsupervised data into the MaxEnt-IRL framework using a pairwise penalty on trajectories. Empirical results in a highway driving and grid-world problems indicate that MESSI is able to take advantage of the unsupervised trajectories and improve the performance of MaxEnt-IRL.
Cite
@article{arxiv.2604.20074,
title = {Maximum Entropy Semi-Supervised Inverse Reinforcement Learning},
author = {Julien Audiffren and Michal Valko and Alessandro Lazaric and Mohammad Ghavamzadeh},
journal= {arXiv preprint arXiv:2604.20074},
year = {2026}
}
Comments
In Proceedings of the 24th International Joint Conference on Artificial Intelligence (IJCAI 2015)